Learning the Sherrington-Kirkpatrick Model Even at Low Temperatureby Gautam Chandrasekaran, Adam KlivansFirst submitted to arxiv…
Infinite Width Limits of Self Supervised Neural Networksby Maximilian Fleissner, Gautham Govind Anil, Debarghya GhoshdastidarFirst…
AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformersby Jake Grigsby, Justin Sasek, Samyak…
PickScan: Object discovery and reconstruction from handheld interactionsby Vincent van der Brugge, Marc Pollefeys, Joshua…
Stealing Training Graphs from Graph Neural Networksby Minhua Lin, Enyan Dai, Junjie Xu, Jinyuan Jia,…
Debiasing Watermarks for Large Language Models via Maximal Couplingby Yangxinyu Xie, Xiang Li, Tanwi Mallick,…
Capturing Sparks of Abstraction for the ARC Challengeby Martin AndrewsFirst submitted to arxiv on: 17…
Reliable Learning of Halfspaces under Gaussian Marginalsby Ilias Diakonikolas, Lisheng Ren, Nikos ZarifisFirst submitted to…
Making Sigmoid-MSE Great Again: Output Reset Challenges Softmax Cross-Entropy in Neural Network Classificationby Kanishka Tyagi,…
Don’t Be So Positive: Negative Step Sizes in Second-Order Methodsby Betty Shea, Mark SchmidtFirst submitted…